Automatic Alt-text: Computer-generated Image Descriptions for Blind Users on a Social Network Service

By Shaomei Wu, J. Wieland, Omid Farivar, Julie Schiller. 2017

280 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Human Factors and Ergonomics, Occupational Therapy, Natural Language Generation, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Human Factors and Ergonomics

In Occupational Therapy

In Natural Language Generation

In Human-Computer Interaction

Citations in the corpus

Improved Image Captioning via Policy Gradient optimization of SPIDEr (2016, background): “This has many applications, including text-based image retrieval, accessibility for blind users [25], and human-robot interaction [6].”
Understanding Blind People's Experiences with Computer-Generated Captions of Social Media Images (2017, background): “Voykinska et al. [29] explored this phenomenon further, focusing on how blind people interact with visual content on Facebook.”
Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making (2021, background): “AI assistance has been shown to improve people’s efficiency in tasks such as transcription by enhancing their computational capacity [16, 35], support creativity in producing music [15, 41, 45], and even allow the visually impaired to “see” images [22, 68].”
From Show to Tell: A Survey on Deep Learning-Based Image Captioning (2021, background): “impaired [235], where image captioning approaches must be able to provide informative descriptions even for low-quality visual inputs [132].”
It Takes Two to Tango: Towards Theory of AI's Mind (2017, background): “However, as other recent works have shown [14, 24], the behavior of an AI agent is often quite different from that of a human – sometimes in ways that are surprising.”
Taxonomizing and Measuring Representational Harms: A Look at Image Tagging (2023, methodology): “For example, image tagging systems are commonly used to generate alt text descriptions of images for blind and low-vision users (Wu et al. 2017), provide search or grouping functionality in photo-management software, and enable users of search engines to ﬁnd images based on their contents as well…”
“It’s Complicated”: Negotiating Accessibility and (Mis)Representation in Image Descriptions of Race, Gender, and Disability (2021, methodology): “Researchers have studied several solutions to increase the number of described images from crowdsourcing [93] to generating them automatically [40, 123].”
"Person, Shoes, Tree. Is the Person Naked?" What People with Vision Impairments Want in Image Descriptions (2020, methodology): “Others focused on BLV participants’ experience with descriptions for images presented on social media platforms and how BLV users perceive automatically generated captions [25, 43, 44].”